What is prompt injection?
An attack technique where malicious instructions are injected into an LLM prompt to bypass safety guidelines or modify system behavior.
Verify This Answer
Cross-check this information using these trusted sources:
More FAQs in How to Prevent Prompt Injection and Secure Your AI Apps
Prompting techniques designed to bypass the built-in safety filters of models to get them to generate prohibited content.
Yes, if not secured, users can write prompts that command the model to output its initial system instructions.
A specialized model developed by Meta specifically to classify inputs and outputs as safe or unsafe.
Still have questions?
Browse all our FAQs or reach out to our support team